Generate Stunning Images with Stable Diffusion 3.5 Medium Cognitive Actions

21 Apr 2025
Generate Stunning Images with Stable Diffusion 3.5 Medium Cognitive Actions

In the evolving landscape of artificial intelligence, the ability to generate high-quality images from text prompts is a game-changer. The Stable Diffusion 3.5 Medium spec from Stability AI offers a powerful set of Cognitive Actions designed for developers looking to harness the capabilities of advanced image generation. This API allows you to create visually stunning images by simply providing descriptive text, making it easier than ever to integrate sophisticated image generation into your applications.

Prerequisites

Before diving into the Cognitive Actions, there are a few prerequisites to keep in mind:

  • API Key: You will need an API key for accessing the Cognitive Actions platform. This key is crucial for authentication when making requests.
  • Basic Setup: Ensure you have the necessary libraries installed to make HTTP requests, such as requests in Python.

Authentication is typically handled by passing the API key in the request headers.

Cognitive Actions Overview

Generate Image with Stable Diffusion 3.5 Medium

The Generate Image with Stable Diffusion 3.5 Medium action utilizes the Stable Diffusion model to produce high-quality images from text prompts. This action is particularly beneficial for applications in creative fields, gaming, and any domain where visual representation is crucial.

Input

The action accepts the following fields in the input schema:

  • seed (optional): An integer seed for reproducibility. If not provided, a random seed is used.
  • image (optional): A URI pointing to an input image for image-to-image generation.
  • steps: An integer (default: 40) that defines the number of iterations for image generation (1-50).
  • prompt: A text description guiding the image generation process.
  • aspectRatio: Specifies the output image's aspect ratio (default: "1:1").
  • outputFormat: The desired output format (default: "webp").
  • guidanceScale: A float that adjusts the adherence to the prompt (default: 5, range: 0-20).
  • outputQuality: An integer that sets the image quality (default: 90, range: 0-100).
  • promptStrength: A float that controls the influence of the prompt in image transformations (default: 0.85).
Example Input
{
  "steps": 40,
  "prompt": "a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars",
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 5,
  "outputQuality": 90,
  "promptStrength": 0.85
}

Output

The action typically returns a URL to the generated image, which can be accessed directly.

Example Output
[
  "https://assets.cognitiveactions.com/invocations/c121cdac-4f18-4916-bfa8-ff651eb122cc/7ac82509-5d6e-4d1d-9ee3-7e811a4d5b70.webp"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how to invoke the Generate Image action:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "80a8cb67-0f8e-4cc1-8a8f-690821a6414c" # Action ID for Generate Image with Stable Diffusion 3.5 Medium

# Construct the input payload based on the action's requirements
payload = {
    "steps": 40,
    "prompt": "a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars",
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 5,
    "outputQuality": 90,
    "promptStrength": 0.85
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload} # Hypothetical structure
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this code snippet, replace the placeholder for the API key with your actual key. The action ID is set for the Generate Image action, and the input JSON payload is constructed based on the provided schema. This code will send a request to the hypothetical endpoint and print the results.

Conclusion

The Stable Diffusion 3.5 Medium Cognitive Action opens up exciting possibilities for developers looking to integrate image generation into their applications. With its straightforward input parameters and high-quality output, you can easily create stunning visuals from text descriptions. Consider experimenting with different prompts and parameters to see how they affect the generated images. Happy coding!

← Back to All Articles